{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HEZXAD7ENL55X2RBQDMWM7M4AP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1e43c62543f7b6474ae9031214738cfda7fed975f2a1216c521a2216f90b133c","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-20T17:50:16Z","title_canon_sha256":"35948f18c0aa08b24b778af27b26344d9032021222c729ec331198e149f9963f"},"schema_version":"1.0","source":{"id":"2406.14540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14540","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14540v2","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14540","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_12","alias_value":"HEZXAD7ENL55","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_16","alias_value":"HEZXAD7ENL55X2RB","created_at":"2026-07-05T11:44:40Z"},{"alias_kind":"pith_short_8","alias_value":"HEZXAD7E","created_at":"2026-07-05T11:44:40Z"}],"graph_snapshots":[{"event_id":"sha256:f3ef8fb02b372b4b9bf244d018693b8738a3f6c8df954664ad69a1d8bd0b54f6","target":"graph","created_at":"2026-07-05T11:44:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.14540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the visual space using existing methods which overlooks precise alignment between each action and the corresponding frame. In this paper, we present IRASim, a novel world model capable of generating videos with fine-grained robot-object interaction details, conditioned on historical observations and robot action trajectories. We train a diffusion transformer and in","authors_text":"Chilam Cheang, Fangqi Zhu, Hongtao Wu, Song Guo, Tao Kong, Yuxiao Liu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-20T17:50:16Z","title":"IRASim: A Fine-Grained World Model for Robot Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14540","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c9e47b24128cd656cf6ae9cd77404ce883110526a45984ee583f99abe449b06","target":"record","created_at":"2026-07-05T11:44:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1e43c62543f7b6474ae9031214738cfda7fed975f2a1216c521a2216f90b133c","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-20T17:50:16Z","title_canon_sha256":"35948f18c0aa08b24b778af27b26344d9032021222c729ec331198e149f9963f"},"schema_version":"1.0","source":{"id":"2406.14540","kind":"arxiv","version":2}},"canonical_sha256":"3933700fe46afbdbea2180d9667d9c03fa6ec3897b1701a13b28cf7c8d7c3b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3933700fe46afbdbea2180d9667d9c03fa6ec3897b1701a13b28cf7c8d7c3b4d","first_computed_at":"2026-07-05T11:44:40.032094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:40.032094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xb7FRjqGXg3oFbWsingEz1nbYMcANWumU5RNdC0sFzCxEqZ3gm3S3+nPc0ylg/KdjARVVAu6ZpzMG+l+tHD0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:40.032539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c9e47b24128cd656cf6ae9cd77404ce883110526a45984ee583f99abe449b06","sha256:f3ef8fb02b372b4b9bf244d018693b8738a3f6c8df954664ad69a1d8bd0b54f6"],"state_sha256":"4a3b579bea6990c40dfdda3ab7129ba04cca0de826f8443b3e7eddde65131faf"}